Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5506 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0341. Min Act: -0.0001

Data Index: 203198 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0324. Min Act: -0.0000

Data Index: 952180 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0310. Min Act: -0.0000

Data Index: 238785 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0306. Min Act: -0.0000

Data Index: 897655 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0295. Min Act: -0.0000

Data Index: 157581 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0288. Min Act: -0.0000

Data Index: 596413 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0292. Min Act: -0.0000

Data Index: 418536 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0301. Min Act: -0.0000

Data Index: 74950 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0290. Min Act: -0.0000

Data Index: 621520 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0285. Min Act: -0.0001

Data Index: 439982 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0283. Min Act: -0.0000

Data Index: 1026472 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0289. Min Act: -0.0000

Data Index: 15270 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0286. Min Act: -0.0000

Data Index: 1556377 (Python Code)

Max Activating Token Index: 1016

Text #13

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0285. Min Act: -0.0001

Data Index: 1327494 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0292. Min Act: -0.0000

Data Index: 983826 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0270. Min Act: -0.0000

Data Index: 95496 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0278. Min Act: -0.0000

Data Index: 234737 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0286. Min Act: -0.0001

Data Index: 1266629 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0281. Min Act: -0.0000

Data Index: 426875 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0274. Min Act: -0.0001

Data Index: 350657 (C4 (Web Text))

Max Activating Token Index: 972